Latent diffusion model for conditional reservoir facies generation

2024/11/01 by Dae-Soo Lee, Daesoo Lee, Oscar Ovanger +4 · 2 citations
Earth and Planetary Sciences · Engineering · #Enhanced Oil Recovery Techniques #Reservoir Engineering and Simulation Methods #Seismic Imaging and Inversion Techniques

paper · doi:10.1016/j.cageo.2024.105750

openalex publication_date 2024/11/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

Creating accurate and geologically realistic reservoir facies based on limited measurements is crucial for field development and reservoir management, especially in the oil and gas sector. Traditional two-point geostatistics, while foundational, often struggle to capture complex geological patterns. Multi-point statistics offers more flexibility, but comes with its own challenges related to pattern configurations and storage limits. With the rise of Generative Adversarial Networks (GANs) and their success in various fields, there has been a shift towards using them for facies generation. However, recent advances in the computer vision domain have shown the superiority of diffusion models over GANs. Motivated by this, a novel Latent Diffusion Model is proposed, which is specifically designed for conditional generation of reservoir facies. The proposed model produces high-fidelity facies realizations that rigorously preserve conditioning data. It significantly outperforms a GAN-based alternative. Our implementation on GitHub: https://released-on-accept . • The first paper to adopt a diffusion model for conditional facies generation, • A novel latent diffusion model, designed for maximal preservation of conditional facies data in generated samples. • Conditional facies generation with high fidelity, sample diversity, and the robust preservation of conditional data.

Citations

• Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks
• Denoising Diffusion Probabilistic Models
• Generative adversarial networks
• Label-Efficient Semantic Segmentation with Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• Differentiable Inverse Modeling with Physics-Constrained Latent Diffusion for Heterogeneous Subsurface Parameter Fields
• 3D latent diffusion models for parameterizing and history matching multiscenario facies systems

Related

• Generating Geological Facies Models with Fidelity to Diversity and Statistics of Training Images using Improved Generative Adversarial Networks
• Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale models
• Latent diffusion models for parameterization and data assimilation of facies-based geomodels
• Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation
• 3D latent diffusion models for parameterizing and history matching multiscenario facies systems